Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning
Citations Over TimeTop 10% of 2022 papers
Abstract
Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge. We introduce CICERO, the first AI agent to achieve human-level performance in Diplomacy, a strategy game involving both cooperation and competition that emphasizes natural language negotiation and tactical coordination between seven players. CICERO integrates a language model with planning and reinforcement learning algorithms by inferring players' beliefs and intentions from its conversations and generating dialogue in pursuit of its plans. Across 40 games of an anonymous online Diplomacy league, CICERO achieved more than double the average score of the human players and ranked in the top 10% of participants who played more than one game.
Related Papers
- → New perspectives on diplomacy: a new theory and practice of diplomacy; New perspectives on diplomacy: contemporary diplomacy in action(2022)1 cited
- Maritime Diplomacy in the 21st Century: Drivers and Challenges(2014)
- → Regional diplomacy: a piece in the neo-medieval puzzle?(2019)5 cited
- On Wu Tingfang's Thought on Diplomacy(2006)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)